© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 21078
    Prev
    Next
    INDEX
    Explanations

    dates and locations embedded in text

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    373
    +0.12
    0.6%
    519
    +0.10
    0.5%
    91
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    519
    +0.12
    0.02
    638
    +0.10
    0.02
    470
    +0.10
    0.02
    Negative Logits
    etheless
    -0.73
    yip
    -0.64
    talk
    -0.62
    ========
    -0.60
     organisers
    -0.59
    abol
    -0.59
    govtrack
    -0.58
    eeper
    -0.58
    ouls
    -0.57
    emies
    -0.57
    POSITIVE LOGITS
     photo
    0.90
     illustration
    0.84
     FILE
    0.84
    FILE
    0.81
     photograph
    0.79
    window
    0.74
     screenshot
    0.72
    Photo
    0.70
     Caption
    0.69
     Image
    0.68
    Activations Density 0.068%

    No Known Activations